Enabling AI for citizen science in fish ecology
Completed
By Community for Data Integration (CDI)
April 20, 2020
Artificial Intelligence (AI) is revolutionizing ecology and conservation by enabling species recognition from photos and videos. Our project evaluates the capacity to expand AI for individual fish recognition for population assessment. The success of this effort would facilitate fisheries analysis at an unprecedented scale by engaging anglers and citizen scientists in imagery collection.This project is one of the first attempts to apply AI towards fish population assessment with citizen science.
Principal Investigator : Nathaniel P Hitt
Co-Investigator : Natalya I Rapstine, Mona (Contractor) Arami, Jeff T Falgout, Benjamin Letcher, Nicholas Polys
Cooperator/Partner : Sophia Liu, Fraser Hayes, Ky Wildermuth, Bryan Kelly, Andy Royle, Jason S Burton
Principal Investigator : Nathaniel P Hitt
Co-Investigator : Natalya I Rapstine, Mona (Contractor) Arami, Jeff T Falgout, Benjamin Letcher, Nicholas Polys
Cooperator/Partner : Sophia Liu, Fraser Hayes, Ky Wildermuth, Bryan Kelly, Andy Royle, Jason S Burton
- Source: USGS Sciencebase (id: 5e9db49c82ce172707fb8cdc)
Brook trout imagery data for individual recognition with deep learning
This Data Release provides imagery data for the development of deep-learning models to recognize individual brook trout (n=435). Images were collected at the Paint Bank State Fish Hatchery (Paint Bank, VA) on August 9, 2021 using a GoPro Hero 9 camera mounted approximately 50 cm above a fish board. The Paint Bank State Fish Hatchery is operated by the Virginia Department of Wildlife...
Annotated fish imagery data for individual and species recognition with deep learning
We provide annotated fish imagery data for use in deep learning models (e.g., convolutional neural networks) for individual and species recognition. For individual recognition models, the dataset consists of annotated .json files of individual brook trout imagery collected at the Eastern Ecological Science Center's Experimental Stream Laboratory. For species recognition models, the...
Comparison of underwater video with electrofishing and dive‐counts for stream fish abundance estimation
Advances in video technology enable new strategies for stream fish research. We compared juvenile (age‐0) and adult (age 1+) Brook Trout Salvelinus fontinalis abundance estimates from underwater video with backpack electrofishing and dive‐count methods across a series of stream pools in Shenandoah National Park, Virginia (n = 41). Video methods estimated greater mean abundance of adult...
Authors
Nathaniel P. Hitt, Karli M Rogers, Craig D. Snyder, C. Andrew Dolloff
Nathaniel (Than) Hitt, PhD (Former Employee)
Research Fish Biologist
Research Fish Biologist
Sophia B. Liu, Ph.D. (Former Employee)
Crowdsourcing, Citizen Science, & Open Innovation Theme Lead
Crowdsourcing, Citizen Science, & Open Innovation Theme Lead
Artificial Intelligence (AI) is revolutionizing ecology and conservation by enabling species recognition from photos and videos. Our project evaluates the capacity to expand AI for individual fish recognition for population assessment. The success of this effort would facilitate fisheries analysis at an unprecedented scale by engaging anglers and citizen scientists in imagery collection.This project is one of the first attempts to apply AI towards fish population assessment with citizen science.
Principal Investigator : Nathaniel P Hitt
Co-Investigator : Natalya I Rapstine, Mona (Contractor) Arami, Jeff T Falgout, Benjamin Letcher, Nicholas Polys
Cooperator/Partner : Sophia Liu, Fraser Hayes, Ky Wildermuth, Bryan Kelly, Andy Royle, Jason S Burton
Principal Investigator : Nathaniel P Hitt
Co-Investigator : Natalya I Rapstine, Mona (Contractor) Arami, Jeff T Falgout, Benjamin Letcher, Nicholas Polys
Cooperator/Partner : Sophia Liu, Fraser Hayes, Ky Wildermuth, Bryan Kelly, Andy Royle, Jason S Burton
- Source: USGS Sciencebase (id: 5e9db49c82ce172707fb8cdc)
Brook trout imagery data for individual recognition with deep learning
This Data Release provides imagery data for the development of deep-learning models to recognize individual brook trout (n=435). Images were collected at the Paint Bank State Fish Hatchery (Paint Bank, VA) on August 9, 2021 using a GoPro Hero 9 camera mounted approximately 50 cm above a fish board. The Paint Bank State Fish Hatchery is operated by the Virginia Department of Wildlife...
Annotated fish imagery data for individual and species recognition with deep learning
We provide annotated fish imagery data for use in deep learning models (e.g., convolutional neural networks) for individual and species recognition. For individual recognition models, the dataset consists of annotated .json files of individual brook trout imagery collected at the Eastern Ecological Science Center's Experimental Stream Laboratory. For species recognition models, the...
Comparison of underwater video with electrofishing and dive‐counts for stream fish abundance estimation
Advances in video technology enable new strategies for stream fish research. We compared juvenile (age‐0) and adult (age 1+) Brook Trout Salvelinus fontinalis abundance estimates from underwater video with backpack electrofishing and dive‐count methods across a series of stream pools in Shenandoah National Park, Virginia (n = 41). Video methods estimated greater mean abundance of adult...
Authors
Nathaniel P. Hitt, Karli M Rogers, Craig D. Snyder, C. Andrew Dolloff
Nathaniel (Than) Hitt, PhD (Former Employee)
Research Fish Biologist
Research Fish Biologist
Sophia B. Liu, Ph.D. (Former Employee)
Crowdsourcing, Citizen Science, & Open Innovation Theme Lead
Crowdsourcing, Citizen Science, & Open Innovation Theme Lead